kernel_optimize_test/kernel/debug/kdb/kdb_bt.c
Douglas Anderson 2277b49258 kdb: Fix stack crawling on 'running' CPUs that aren't the master
In kdb when you do 'btc' (back trace on CPU) it doesn't necessarily
give you the right info.  Specifically on many architectures
(including arm64, where I tested) you can't dump the stack of a
"running" process that isn't the process running on the current CPU.
This can be seen by this:

 echo SOFTLOCKUP > /sys/kernel/debug/provoke-crash/DIRECT
 # wait 2 seconds
 <sysrq>g

Here's what I see now on rk3399-gru-kevin.  I see the stack crawl for
the CPU that handled the sysrq but everything else just shows me stuck
in __switch_to() which is bogus:

======

[0]kdb> btc
btc: cpu status: Currently on cpu 0
Available cpus: 0, 1-3(I), 4, 5(I)
Stack traceback for pid 0
0xffffff801101a9c0        0        0  1    0   R  0xffffff801101b3b0 *swapper/0
Call trace:
 dump_backtrace+0x0/0x138
 ...
 kgdb_compiled_brk_fn+0x34/0x44
 ...
 sysrq_handle_dbg+0x34/0x5c
Stack traceback for pid 0
0xffffffc0f175a040        0        0  1    1   I  0xffffffc0f175aa30  swapper/1
Call trace:
 __switch_to+0x1e4/0x240
 0xffffffc0f65616c0
Stack traceback for pid 0
0xffffffc0f175d040        0        0  1    2   I  0xffffffc0f175da30  swapper/2
Call trace:
 __switch_to+0x1e4/0x240
 0xffffffc0f65806c0
Stack traceback for pid 0
0xffffffc0f175b040        0        0  1    3   I  0xffffffc0f175ba30  swapper/3
Call trace:
 __switch_to+0x1e4/0x240
 0xffffffc0f659f6c0
Stack traceback for pid 1474
0xffffffc0dde8b040     1474      727  1    4   R  0xffffffc0dde8ba30  bash
Call trace:
 __switch_to+0x1e4/0x240
 __schedule+0x464/0x618
 0xffffffc0dde8b040
Stack traceback for pid 0
0xffffffc0f17b0040        0        0  1    5   I  0xffffffc0f17b0a30  swapper/5
Call trace:
 __switch_to+0x1e4/0x240
 0xffffffc0f65dd6c0

===

The problem is that 'btc' eventually boils down to
  show_stack(task_struct, NULL);

...and show_stack() doesn't work for "running" CPUs because their
registers haven't been stashed.

On x86 things might work better (I haven't tested) because kdb has a
special case for x86 in kdb_show_stack() where it passes the stack
pointer to show_stack().  This wouldn't work on arm64 where the stack
crawling function seems needs the "fp" and "pc", not the "sp" which is
presumably why arm64's show_stack() function totally ignores the "sp"
parameter.

NOTE: we _can_ get a good stack dump for all the cpus if we manually
switch each one to the kdb master and do a back trace.  AKA:
  cpu 4
  bt
...will give the expected trace.  That's because now arm64's
dump_backtrace will now see that "tsk == current" and go through a
different path.

In this patch I fix the problems by catching a request to stack crawl
a task that's running on a CPU and then I ask that CPU to do the stack
crawl.

NOTE: this will (presumably) change what stack crawls are printed for
x86 machines.  Now kdb functions will show up in the stack crawl.
Presumably this is OK but if it's not we can go back and add a special
case for x86 again.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
2019-10-10 16:28:48 +01:00

221 lines
5.2 KiB
C

/*
* Kernel Debugger Architecture Independent Stack Traceback
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (c) 1999-2004 Silicon Graphics, Inc. All Rights Reserved.
* Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved.
*/
#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
#include <linux/kdb.h>
#include <linux/nmi.h>
#include "kdb_private.h"
static void kdb_show_stack(struct task_struct *p, void *addr)
{
int old_lvl = console_loglevel;
console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
kdb_trap_printk++;
if (!addr && kdb_task_has_cpu(p))
kdb_dump_stack_on_cpu(kdb_process_cpu(p));
else
show_stack(p, addr);
console_loglevel = old_lvl;
kdb_trap_printk--;
}
/*
* kdb_bt
*
* This function implements the 'bt' command. Print a stack
* traceback.
*
* bt [<address-expression>] (addr-exp is for alternate stacks)
* btp <pid> Kernel stack for <pid>
* btt <address-expression> Kernel stack for task structure at
* <address-expression>
* bta [DRSTCZEUIMA] All useful processes, optionally
* filtered by state
* btc [<cpu>] The current process on one cpu,
* default is all cpus
*
* bt <address-expression> refers to a address on the stack, that location
* is assumed to contain a return address.
*
* btt <address-expression> refers to the address of a struct task.
*
* Inputs:
* argc argument count
* argv argument vector
* Outputs:
* None.
* Returns:
* zero for success, a kdb diagnostic if error
* Locking:
* none.
* Remarks:
* Backtrack works best when the code uses frame pointers. But even
* without frame pointers we should get a reasonable trace.
*
* mds comes in handy when examining the stack to do a manual traceback or
* to get a starting point for bt <address-expression>.
*/
static int
kdb_bt1(struct task_struct *p, unsigned long mask, bool btaprompt)
{
char buffer[2];
if (kdb_getarea(buffer[0], (unsigned long)p) ||
kdb_getarea(buffer[0], (unsigned long)(p+1)-1))
return KDB_BADADDR;
if (!kdb_task_state(p, mask))
return 0;
kdb_printf("Stack traceback for pid %d\n", p->pid);
kdb_ps1(p);
kdb_show_stack(p, NULL);
if (btaprompt) {
kdb_getstr(buffer, sizeof(buffer),
"Enter <q> to end, <cr> to continue:");
if (buffer[0] == 'q') {
kdb_printf("\n");
return 1;
}
}
touch_nmi_watchdog();
return 0;
}
static void
kdb_bt_cpu(unsigned long cpu)
{
struct task_struct *kdb_tsk;
if (cpu >= num_possible_cpus() || !cpu_online(cpu)) {
kdb_printf("WARNING: no process for cpu %ld\n", cpu);
return;
}
/* If a CPU failed to round up we could be here */
kdb_tsk = KDB_TSK(cpu);
if (!kdb_tsk) {
kdb_printf("WARNING: no task for cpu %ld\n", cpu);
return;
}
kdb_set_current_task(kdb_tsk);
kdb_bt1(kdb_tsk, ~0UL, false);
}
int
kdb_bt(int argc, const char **argv)
{
int diag;
int btaprompt = 1;
int nextarg;
unsigned long addr;
long offset;
/* Prompt after each proc in bta */
kdbgetintenv("BTAPROMPT", &btaprompt);
if (strcmp(argv[0], "bta") == 0) {
struct task_struct *g, *p;
unsigned long cpu;
unsigned long mask = kdb_task_state_string(argc ? argv[1] :
NULL);
if (argc == 0)
kdb_ps_suppressed();
/* Run the active tasks first */
for_each_online_cpu(cpu) {
p = kdb_curr_task(cpu);
if (kdb_bt1(p, mask, btaprompt))
return 0;
}
/* Now the inactive tasks */
kdb_do_each_thread(g, p) {
if (KDB_FLAG(CMD_INTERRUPT))
return 0;
if (task_curr(p))
continue;
if (kdb_bt1(p, mask, btaprompt))
return 0;
} kdb_while_each_thread(g, p);
} else if (strcmp(argv[0], "btp") == 0) {
struct task_struct *p;
unsigned long pid;
if (argc != 1)
return KDB_ARGCOUNT;
diag = kdbgetularg((char *)argv[1], &pid);
if (diag)
return diag;
p = find_task_by_pid_ns(pid, &init_pid_ns);
if (p) {
kdb_set_current_task(p);
return kdb_bt1(p, ~0UL, false);
}
kdb_printf("No process with pid == %ld found\n", pid);
return 0;
} else if (strcmp(argv[0], "btt") == 0) {
if (argc != 1)
return KDB_ARGCOUNT;
diag = kdbgetularg((char *)argv[1], &addr);
if (diag)
return diag;
kdb_set_current_task((struct task_struct *)addr);
return kdb_bt1((struct task_struct *)addr, ~0UL, false);
} else if (strcmp(argv[0], "btc") == 0) {
unsigned long cpu = ~0;
struct task_struct *save_current_task = kdb_current_task;
if (argc > 1)
return KDB_ARGCOUNT;
if (argc == 1) {
diag = kdbgetularg((char *)argv[1], &cpu);
if (diag)
return diag;
}
if (cpu != ~0) {
kdb_bt_cpu(cpu);
} else {
/*
* Recursive use of kdb_parse, do not use argv after
* this point.
*/
argv = NULL;
kdb_printf("btc: cpu status: ");
kdb_parse("cpu\n");
for_each_online_cpu(cpu) {
kdb_bt_cpu(cpu);
touch_nmi_watchdog();
}
kdb_set_current_task(save_current_task);
}
return 0;
} else {
if (argc) {
nextarg = 1;
diag = kdbgetaddrarg(argc, argv, &nextarg, &addr,
&offset, NULL);
if (diag)
return diag;
kdb_show_stack(kdb_current_task, (void *)addr);
return 0;
} else {
return kdb_bt1(kdb_current_task, ~0UL, false);
}
}
/* NOTREACHED */
return 0;
}